Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions. Code, demo, video and visualization are available at: https://disco-dance.github.io/.
The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have further undermined the trustworthiness of NLP systems, leading to unreliable model explanations that are merely correlated with the output predictions. To encourage fairness and transparency, there exists an urgent demand for reliable explanations that allow users to consistently understand the model's behavior. In this work, we propose a complete framework for extending concept-based interpretability methods to NLP. Specifically, we propose a post-hoc interpretability method for extracting predictive high-level features (concepts) from the pretrained model's hidden layer activations. We optimize for features whose existence causes the output predictions to change substantially, \ie generates a high impact. Moreover, we devise several evaluation metrics that can be universally applied. Extensive experiments on real and synthetic tasks demonstrate that our method achieves superior results on {predictive impact}, usability, and faithfulness compared to the baselines.
This study explores the concept of equivariance in vision-language foundation models (VLMs), focusing specifically on the multimodal similarity function that is not only the major training objective but also the core delivery to support downstream tasks. Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes. This allows VLMs to generalize better to nuanced and unseen multimodal compositions. However, modeling equivariance is challenging as the ground truth of semantic change is difficult to collect. For example, given an image-text pair about a dog, it is unclear to what extent the similarity changes when the pixel is changed from dog to cat? To this end, we propose EqSim, a regularization loss that can be efficiently calculated from any two matched training pairs and easily pluggable into existing image-text retrieval fine-tuning. Meanwhile, to further diagnose the equivariance of VLMs, we present a new challenging benchmark EqBen. Compared to the existing evaluation sets, EqBen is the first to focus on "visual-minimal change". Extensive experiments show the lack of equivariance in current VLMs and validate the effectiveness of EqSim. Code is available at \url{https://github.com/Wangt-CN/EqBen}.
We are interested in learning robust models from insufficient data, without the need for any externally pre-trained checkpoints. First, compared to sufficient data, we show why insufficient data renders the model more easily biased to the limited training environments that are usually different from testing. For example, if all the training swan samples are "white", the model may wrongly use the "white" environment to represent the intrinsic class swan. Then, we justify that equivariance inductive bias can retain the class feature while invariance inductive bias can remove the environmental feature, leaving the class feature that generalizes to any environmental changes in testing. To impose them on learning, for equivariance, we demonstrate that any off-the-shelf contrastive-based self-supervised feature learning method can be deployed; for invariance, we propose a class-wise invariant risk minimization (IRM) that efficiently tackles the challenge of missing environmental annotation in conventional IRM. State-of-the-art experimental results on real-world benchmarks (VIPriors, ImageNet100 and NICO) validate the great potential of equivariance and invariance in data-efficient learning. The code is available at https://github.com/Wangt-CN/EqInv
The task of video virtual try-on aims to fit the target clothes to a person in the video with spatio-temporal consistency. Despite tremendous progress of image virtual try-on, they lead to inconsistency between frames when applied to videos. Limited work also explored the task of video-based virtual try-on but failed to produce visually pleasing and temporally coherent results. Moreover, there are two other key challenges: 1) how to generate accurate warping when occlusions appear in the clothing region; 2) how to generate clothes and non-target body parts (e.g. arms, neck) in harmony with the complicated background; To address them, we propose a novel video virtual try-on framework, ClothFormer, which successfully synthesizes realistic, harmonious, and spatio-temporal consistent results in complicated environment. In particular, ClothFormer involves three major modules. First, a two-stage anti-occlusion warping module that predicts an accurate dense flow mapping between the body regions and the clothing regions. Second, an appearance-flow tracking module utilizes ridge regression and optical flow correction to smooth the dense flow sequence and generate a temporally smooth warped clothing sequence. Third, a dual-stream transformer extracts and fuses clothing textures, person features, and environment information to generate realistic try-on videos. Through rigorous experiments, we demonstrate that our method highly surpasses the baselines in terms of synthesized video quality both qualitatively and quantitatively.
Extracting class activation maps (CAM) is arguably the most standard step of generating pseudo masks for weakly-supervised semantic segmentation (WSSS). Yet, we find that the crux of the unsatisfactory pseudo masks is the binary cross-entropy loss (BCE) widely used in CAM. Specifically, due to the sum-over-class pooling nature of BCE, each pixel in CAM may be responsive to multiple classes co-occurring in the same receptive field. As a result, given a class, its hot CAM pixels may wrongly invade the area belonging to other classes, or the non-hot ones may be actually a part of the class. To this end, we introduce an embarrassingly simple yet surprisingly effective method: Reactivating the converged CAM with BCE by using softmax cross-entropy loss (SCE), dubbed \textbf{ReCAM}. Given an image, we use CAM to extract the feature pixels of each single class, and use them with the class label to learn another fully-connected layer (after the backbone) with SCE. Once converged, we extract ReCAM in the same way as in CAM. Thanks to the contrastive nature of SCE, the pixel response is disentangled into different classes and hence less mask ambiguity is expected. The evaluation on both PASCAL VOC and MS~COCO shows that ReCAM not only generates high-quality masks, but also supports plug-and-play in any CAM variant with little overhead.
A good visual representation is an inference map from observations (images) to features (vectors) that faithfully reflects the hidden modularized generative factors (semantics). In this paper, we formulate the notion of "good" representation from a group-theoretic view using Higgins' definition of disentangled representation, and show that existing Self-Supervised Learning (SSL) only disentangles simple augmentation features such as rotation and colorization, thus unable to modularize the remaining semantics. To break the limitation, we propose an iterative SSL algorithm: Iterative Partition-based Invariant Risk Minimization (IP-IRM), which successfully grounds the abstract semantics and the group acting on them into concrete contrastive learning. At each iteration, IP-IRM first partitions the training samples into two subsets that correspond to an entangled group element. Then, it minimizes a subset-invariant contrastive loss, where the invariance guarantees to disentangle the group element. We prove that IP-IRM converges to a fully disentangled representation and show its effectiveness on various benchmarks. Codes are available at https://github.com/Wangt-CN/IP-IRM.
Attention module does not always help deep models learn causal features that are robust in any confounding context, e.g., a foreground object feature is invariant to different backgrounds. This is because the confounders trick the attention to capture spurious correlations that benefit the prediction when the training and testing data are IID (identical & independent distribution); while harm the prediction when the data are OOD (out-of-distribution). The sole fundamental solution to learn causal attention is by causal intervention, which requires additional annotations of the confounders, e.g., a "dog" model is learned within "grass+dog" and "road+dog" respectively, so the "grass" and "road" contexts will no longer confound the "dog" recognition. However, such annotation is not only prohibitively expensive, but also inherently problematic, as the confounders are elusive in nature. In this paper, we propose a causal attention module (CaaM) that self-annotates the confounders in unsupervised fashion. In particular, multiple CaaMs can be stacked and integrated in conventional attention CNN and self-attention Vision Transformer. In OOD settings, deep models with CaaM outperform those without it significantly; even in IID settings, the attention localization is also improved by CaaM, showing a great potential in applications that require robust visual saliency. Codes are available at \url{https://github.com/Wangt-CN/CaaM}.
We unveil a long-standing problem in the prevailing co-saliency detection systems: there is indeed inconsistency between training and testing. Constructing a high-quality co-saliency detection dataset involves time-consuming and labor-intensive pixel-level labeling, which has forced most recent works to rely instead on semantic segmentation or saliency detection datasets for training. However, the lack of proper co-saliency and the absence of multiple foreground objects in these datasets can lead to spurious variations and inherent biases learned by models. To tackle this, we introduce the idea of counterfactual training through context adjustment, and propose a "cost-free" group-cut-paste (GCP) procedure to leverage images from off-the-shelf saliency detection datasets and synthesize new samples. Following GCP, we collect a novel dataset called Context Adjustment Training. The two variants of our dataset, i.e., CAT and CAT+, consist of 16,750 and 33,500 images, respectively. All images are automatically annotated with high-quality masks. As a side-product, object categories, as well as edge information, are also provided to facilitate other related works. Extensive experiments with state-of-the-art models are conducted to demonstrate the superiority of our dataset. We hope that the scale, diversity, and quality of CAT/CAT+ can benefit researchers in this area and beyond. The dataset and benchmark toolkit will be accessible through our project page.
We present a novel counterfactual framework for both Zero-Shot Learning (ZSL) and Open-Set Recognition (OSR), whose common challenge is generalizing to the unseen-classes by only training on the seen-classes. Our idea stems from the observation that the generated samples for unseen-classes are often out of the true distribution, which causes severe recognition rate imbalance between the seen-class (high) and unseen-class (low). We show that the key reason is that the generation is not Counterfactual Faithful, and thus we propose a faithful one, whose generation is from the sample-specific counterfactual question: What would the sample look like, if we set its class attribute to a certain class, while keeping its sample attribute unchanged? Thanks to the faithfulness, we can apply the Consistency Rule to perform unseen/seen binary classification, by asking: Would its counterfactual still look like itself? If ``yes'', the sample is from a certain class, and ``no'' otherwise. Through extensive experiments on ZSL and OSR, we demonstrate that our framework effectively mitigates the seen/unseen imbalance and hence significantly improves the overall performance. Note that this framework is orthogonal to existing methods, thus, it can serve as a new baseline to evaluate how ZSL/OSR models generalize. Codes are available at https://github.com/yue-zhongqi/gcm-cf.