Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating compe... more Transformer emerges as a powerful tool for visual recognition. In addition to demonstrating competitive performance on a broad range of visual benchmarks, recent works also argue that Transformers are much more robust than Convolutions Neural Networks (CNNs). Nonetheless, surprisingly, we find these conclusions are drawn from unfair experimental settings, where Transformers and CNNs are compared at different scales and are applied with distinct training frameworks. In this paper, we aim to provide the first fair & in-depth comparisons between Transformers and CNNs, focusing on robustness evaluations. With our unified training setup, we first challenge the previous belief that Transformers outshine CNNs when measuring adversarial robustness. More surprisingly, we find CNNs can easily be as robust as Transformers on defending against adversarial attacks, if they properly adopt Transformers’ training recipes. While regarding generalization on out-of-distribution samples, we show pretra...
In this work we present point-level region contrast, a self-supervised pre-training approach for ... more In this work we present point-level region contrast, a self-supervised pre-training approach for the task of object detection. This approach is motivated by the two key factors in detection: localization and recognition. While accurate localization favors models that operate at the pixel- or point-level, correct recognition typically relies on a more holistic, region-level view of objects. Incorporating this perspective in pre-training, our approach performs contrastive learning by directly sampling individual point pairs from different regions. Compared to an aggregated representation per region, our approach is more robust to the change in input region quality, and further enables us to implicitly improve initial region assignments via online knowledge distillation during training. Both advantages are important when dealing with imperfect regions encountered in the unsupervised setting. Experiments show point-level region contrast improves on state-of-the-art pre-training methods ...
Referring object detection and referring image segmentation are important tasks that require join... more Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly o...
3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumour... more 3D convolution neural networks (CNN) have been proved very successful in parsing organs or tumours in 3D medical images, but it remains sophisticated and time-consuming to choose or design proper 3D networks given different task contexts. Recently, Neural Architecture Search (NAS) is proposed to solve this problem by searching for the best network architecture automatically. However, the inconsistency between search stage and deployment stage often exists in NAS algorithms due to memory constraints and large search space, which could become more serious when applying NAS to some memory and time consuming tasks, such as 3D medical image segmentation. In this paper, we propose coarse-to-fine neural architecture search (C2FNAS) to automatically search a 3D segmentation network from scratch without inconsistency on network size or input size. Specifically, we divide the search procedure into two stages: 1) the coarse stage, where we search the macro-level topology of the network, i.e. h...
Detecting semantic parts of an object is a challenging task in computer vision, particularly beca... more Detecting semantic parts of an object is a challenging task in computer vision, particularly because it is hard to construct large annotated datasets due to the difficulty of annotating semantic parts. In this paper we present an approach which learns from a small training dataset of annotated semantic parts, where the object is seen from a limited range of viewpoints, but generalizes to detect semantic parts from a much larger range of viewpoints. Our approach is based on a matching algorithm for finding accurate spatial correspondence between two images, which enables semantic parts annotated on one image to be transplanted to another. In particular, this enables images in the training dataset to be matched to a virtual 3D model of the object (for simplicity, we assume that the object viewpoint can be estimated by standard techniques). Then a clustering algorithm is used to annotate the semantic parts of the 3D virtual model. This virtual 3D model can be used to synthesize annotat...
Recently, there emerges a series of vision Transformers, which show superior performance with a m... more Recently, there emerges a series of vision Transformers, which show superior performance with a more compact model size than conventional convolutional neural networks, thanks to the strong ability of Transformers to model long-range dependencies. However, the advantages of vision Transformers also come with a price: Self-attention, the core part of Transformer, has a quadratic complexity to the input sequence length. This leads to a dramatic increase of computation and memory cost with the increase of sequence length, thus introducing difficulties when applying Transformers to the vision tasks that require dense predictions based on high-resolution feature maps. In this paper, we propose a new vision Transformer, named Glance-and-Gaze Transformer (GG-Transformer), to address the aforementioned issues. It is motivated by the Glance and Gaze behavior of human beings when recognizing objects in natural scenes, with the ability to efficiently model both long-range dependencies and loca...
Today's most popular approaches to keypoint detection learn a holistic representation of all ... more Today's most popular approaches to keypoint detection learn a holistic representation of all keypoints. This enables them to implicitly leverage the relative spatial geometry between keypoints and thus to prevent false-positive detections due to local ambiguities. However, our experiments show that such holistic representations do not generalize well when the 3D pose of objects varies strongly, or when objects are partially occluded. In this paper, we propose CoKe, a framework for the supervised contrastive learning of distinct local feature representations for robust keypoint detection. In particular, we introduce a feature bank mechanism and update rules for keypoint and non-keypoint features which make possible to learn local keypoint detectors that are accurate and robust to local ambiguities. Our experiments show that CoKe achieves state-of-the-art results compared to approaches that jointly represent all keypoints holistically (Stacked Hourglass Networks, MSS-Net) as well ...
Leveraging temporal information has been regarded as essential for developing video understanding... more Leveraging temporal information has been regarded as essential for developing video understanding models. However, how to properly incorporate temporal information into the recent successful instance discrimination based contrastive self-supervised learning (CSL) framework remains unclear. As an intuitive solution, we find that directly applying temporal augmentations does not help, or even impair video CSL in general. This counter-intuitive observation motivates us to re-design existing video CSL frameworks, for better integration of temporal knowledge. To this end, we present Temporal-aware Contrastive self-supervised learningTaCo, as a general paradigm to enhance video CSL. Specifically, TaCo selects a set of temporal transformations not only as strong data augmentation but also to constitute extra self-supervision for video understanding. By jointly contrasting instances with enriched temporal transformations and learning these transformations as self-supervised signals, TaCo ca...
Understanding objects in terms of their individual parts is important, because it enables a preci... more Understanding objects in terms of their individual parts is important, because it enables a precise understanding of the objects' geometrical structure, and enhances object recognition when the object is seen in a novel pose or under partial occlusion. However, the manual annotation of parts in large scale datasets is time consuming and expensive. In this paper, we aim at discovering object parts in an unsupervised manner, i.e., without ground-truth part or keypoint annotations. Our approach builds on the intuition that objects of the same class in a similar pose should have their parts aligned at similar spatial locations. We exploit the property that neural network features are largely invariant to nuisance variables and the main remaining source of variations between images of the same object category is the object pose. Specifically, given a training image, we find a set of similar images that show instances of the same object category in the same pose, through an affine ali...
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Input MG (ours) CA [18] GCA [24] BSHM [27] Photoshop Figure 1: A visual comparison of MG and othe... more Input MG (ours) CA [18] GCA [24] BSHM [27] Photoshop Figure 1: A visual comparison of MG and other matting methods including the commercial matting method in Photoshop. The guidance input (see Sec. 5 for details.) is located at the bottom-left of each image. Note that BSHM [27] has an internal segmentation prediction network thus does not take external mask. Best viewed zoomed in.
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 1, 2019
Referring object detection and referring image segmentation are important tasks that require join... more Referring object detection and referring image segmentation are important tasks that require joint understanding of visual information and natural language. Yet there has been evidence that current benchmark datasets suffer from bias, and current state-of-the-art models cannot be easily evaluated on their intermediate reasoning process. To address these issues and complement similar efforts in visual question answering, we build CLEVR-Ref+, a synthetic diagnostic dataset for referring expression comprehension. The precise locations and attributes of the objects are readily available, and the referring expressions are automatically associated with functional programs. The synthetic nature allows control over dataset bias (through sampling strategy), and the modular programs enable intermediate reasoning ground truth without human annotators. In addition to evaluating several state-of-the-art models on CLEVR-Ref+, we also propose IEP-Ref, a module network approach that significantly outperforms other models on our dataset. In particular, we present two interesting and important findings using IEP-Ref: (1) the module trained to transform feature maps into segmentation masks can be attached to any intermediate module to reveal the entire reasoning process step-by-step; (2) even if all training data has at least one object referred, IEP-Ref can correctly predict no-foreground when presented with false-premise referring expressions. To the best of our knowledge, this is the first direct and quantitative proof that neural modules behave in the way they are intended. 1
Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is... more Fine-grained visual classification (FGVC) which aims at recognizing objects from subcategories is a very challenging task due to the inherently subtle inter-class differences. Recent works mainly tackle this problem by focusing on how to locate the most discriminative image regions and rely on them to improve the capability of networks to capture subtle variances. Most of these works achieve this by reusing the backbone network to extract features of selected regions. However, this strategy inevitably complicates the pipeline and pushes the proposed regions to contain most parts of the objects. Recently, vision transformer (ViT) shows its strong performance in the traditional classification task. The self-attention mechanism of the transformer links every patch token to the classification token. The strength of the attention link can be intuitively considered as an indicator of the importance of tokens. In this work, we propose a novel transformer-based framework TransFG where we in...
2019 IEEE/CVF International Conference on Computer Vision (ICCV), Oct 1, 2019
Detecting semantic parts of an object is a challenging task, particularly because it is hard to a... more Detecting semantic parts of an object is a challenging task, particularly because it is hard to annotate semantic parts and construct large datasets. In this paper, we present an approach which can learn from a small annotated dataset containing a limited range of viewpoints and generalize to detect semantic parts for a much larger range of viewpoints. The approach is based on our matching algorithm, which is used for finding accurate spatial correspondence between two images and transplanting semantic parts annotated on one image to the other. Images in the training set are matched to synthetic images rendered from a 3D CAD model, following which a clustering algorithm is used to automatically annotate semantic parts of the CAD model. During the testing period, this CAD model can synthesize annotated images under every viewpoint. These synthesized images are matched to images in the testing set to detect semantic parts in novel viewpoints. Our algorithm is simple, intuitive, and contains very few parameters. Experiments show our method outperforms standard deep learning approaches and, in particular, performs much better on novel viewpoints. For facilitating the future research, code is available: https://github.com/ytongbai/SemanticPartDetection
Uploads
Papers by Yutong Bai