Self-supervised video representation learning aimed at maximizing similarity between different temporal segments of one video, in order to enforce feature persistence over time. This leads to loss of pertinent information related to temporal relationships, rendering actions such as `enter' and `leave' to be indistinguishable. To mitigate this limitation, we propose Latent Time Navigation (LTN), a time-parameterized contrastive learning strategy that is streamlined to capture fine-grained motions. Specifically, we maximize the representation similarity between different video segments from one video, while maintaining their representations time-aware along a subspace of the latent representation code including an orthogonal basis to represent temporal changes. Our extensive experimental analysis suggests that learning video representations by LTN consistently improves performance of action classification in fine-grained and human-oriented tasks (e.g., on Toyota Smarthome dataset). In addition, we demonstrate that our proposed model, when pre-trained on Kinetics-400, generalizes well onto the unseen real world video benchmark datasets UCF101 and HMDB51, achieving state-of-the-art performance in action recognition.
Currently, learning better unsupervised sentence representations is the pursuit of many natural language processing communities. Lots of approaches based on pre-trained language models (PLMs) and contrastive learning have achieved promising results on this task. Experimentally, we observe that the over-smoothing problem reduces the capacity of these powerful PLMs, leading to sub-optimal sentence representations. In this paper, we present a Simple method named Self-Contrastive Learning (SSCL) to alleviate this issue, which samples negatives from PLMs intermediate layers, improving the quality of the sentence representation. Our proposed method is quite simple and can be easily extended to various state-of-the-art models for performance boosting, which can be seen as a plug-and-play contrastive framework for learning unsupervised sentence representation. Extensive results prove that SSCL brings the superior performance improvements of different strong baselines (e.g., BERT and SimCSE) on Semantic Textual Similarity and Transfer datasets. Our codes are available at https://github.com/nuochenpku/SSCL.
Commonsense question answering (QA) research requires machines to answer questions based on commonsense knowledge. However, this research requires expensive labor costs to annotate data as the basis of research, and models that rely on fine-tuning paradigms only apply to specific tasks, rather than learn a general commonsense reasoning ability. As a more robust method, zero-shot commonsense question answering shows a good prospect. The current zero-shot framework tries to convert triples in commonsense knowledge graphs (KGs) into QA-form samples as the pre-trained data source to incorporate commonsense knowledge into the model. However, this method ignores the multi-hop relationship in the KG, which is also an important central problem in commonsense reasoning. In this paper, we propose a novel multi-hop commonsense knowledge injection framework. Specifically, it explores multi-hop reasoning paradigm in KGs that conform to linguistic logic, and we further propose two multi-hop QA generation methods based on KGs. Then, we utilize contrastive learning to pre-train the model with the synthetic QA dataset to inject multi-hop commonsense knowledge. Extensive experiments on five commonsense question answering benchmarks demonstrate that our framework achieves state-of-art performance.
In this work, we present an unsupervised retrieval method with contrastive learning on web anchors. The anchor text describes the content that is referenced from the linked page. This shows similarities to search queries that aim to retrieve pertinent information from relevant documents. Based on their commonalities, we train an unsupervised dense retriever, Anchor-DR, with a contrastive learning task that matches the anchor text and the linked document. To filter out uninformative anchors (such as ``homepage'' or other functional anchors), we present a novel filtering technique to only select anchors that contain similar types of information as search queries. Experiments show that Anchor-DR outperforms state-of-the-art methods on unsupervised dense retrieval by a large margin (e.g., by 5.3% NDCG@10 on MSMARCO). The gain of our method is especially significant for search and question answering tasks. Our analysis further reveals that the pattern of anchor-document pairs is similar to that of search query-document pairs. Code available at https://github.com/Veronicium/AnchorDR.
FinTech lending (e.g., micro-lending) has played a significant role in facilitating financial inclusion. It has reduced processing times and costs, enhanced the user experience, and made it possible for people to obtain loans who may not have qualified for credit from traditional lenders. However, there are concerns about the potentially biased algorithmic decision-making during loan screening. Machine learning algorithms used to evaluate credit quality can be influenced by representation bias in the training data, as we only have access to the default outcome labels of approved loan applications, for which the borrowers' socioeconomic characteristics are better than those of rejected ones. In this case, the model trained on the labeled data performs well on the historically approved population, but does not generalize well to borrowers of low socioeconomic background. In this paper, we investigate the problem of representation bias in loan screening for a real-world FinTech lending platform. We propose a new Transformer-based sequential loan screening model with self-supervised contrastive learning and domain adaptation to tackle this challenging issue. We use contrastive learning to train our feature extractor on unapproved (unlabeled) loan applications and use domain adaptation to generalize the performance of our label predictor. We demonstrate the effectiveness of our model through extensive experimentation in the real-world micro-lending setting. Our results show that our model significantly promotes the inclusiveness of funding decisions, while also improving loan screening accuracy and profit by 7.10% and 8.95%, respectively. We also show that incorporating the test data into contrastive learning and domain adaptation and labeling a small ratio of test data can further boost model performance.
In this paper, we address the problem of generalized category discovery (GCD), \ie, given a set of images where part of them are labelled and the rest are not, the task is to automatically cluster the images in the unlabelled data, leveraging the information from the labelled data, while the unlabelled data contain images from the labelled classes and also new ones. GCD is similar to semi-supervised learning (SSL) but is more realistic and challenging, as SSL assumes all the unlabelled images are from the same classes as the labelled ones. We also do not assume the class number in the unlabelled data is known a-priori, making the GCD problem even harder. To tackle the problem of GCD without knowing the class number, we propose an EM-like framework that alternates between representation learning and class number estimation. We propose a semi-supervised variant of the Gaussian Mixture Model (GMM) with a stochastic splitting and merging mechanism to dynamically determine the prototypes by examining the cluster compactness and separability. With these prototypes, we leverage prototypical contrastive learning for representation learning on the partially labelled data subject to the constraints imposed by the labelled data. Our framework alternates between these two steps until convergence. The cluster assignment for an unlabelled instance can then be retrieved by identifying its nearest prototype. We comprehensively evaluate our framework on both generic image classification datasets and challenging fine-grained object recognition datasets, achieving state-of-the-art performance.
Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision tasks, attributed to representations learned by contrasting the same/different classes of entities. Without access to true labels, positive points are predicted using pseudo-labels that are inherently noisy, and negative points often require large batches or momentum encoders, resulting in unreliable similarity information and a high computational overhead. In this paper, we rethink a state-of-the-art contrastive PLL method PiCO[24], inspiring the design of a simple framework termed PaPi (Partial-label learning with a guided Prototypical classifier), which demonstrates significant scope for improvement in representation learning, thus contributing to label disambiguation. PaPi guides the optimization of a prototypical classifier by a linear classifier with which they share the same feature encoder, thus explicitly encouraging the representation to reflect visual similarity between categories. It is also technically appealing, as PaPi requires only a few components in PiCO with the opposite direction of guidance, and directly eliminates the contrastive learning module that would introduce noise and consume computational resources. We empirically demonstrate that PaPi significantly outperforms other PLL methods on various image classification tasks.
Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for text-guided image editing, namely \texttt{iEdit}, that generates images conditioned on a source image and a textual edit prompt. As a fully-annotated dataset with target images does not exist, previous approaches perform subject-specific fine-tuning at test time or adopt contrastive learning without a target image, leading to issues on preserving the fidelity of the source image. We propose to automatically construct a dataset derived from LAION-5B, containing pseudo-target images with their descriptive edit prompts given input image-caption pairs. This dataset gives us the flexibility of introducing a weakly-supervised loss function to generate the pseudo-target image from the latent noise of the source image conditioned on the edit prompt. To encourage localised editing and preserve or modify spatial structures in the image, we propose a loss function that uses segmentation masks to guide the editing during training and optionally at inference. Our model is trained on the constructed dataset with 200K samples and constrained GPU resources. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
ROI extraction is an active but challenging task in remote sensing because of the complicated landform, the complex boundaries and the requirement of annotations. Weakly supervised learning (WSL) aims at learning a mapping from input image to pixel-wise prediction under image-wise labels, which can dramatically decrease the labor cost. However, due to the imprecision of labels, the accuracy and time consumption of WSL methods are relatively unsatisfactory. In this paper, we propose a two-step ROI extraction based on contractive learning. Firstly, we present to integrate multiscale Grad-CAM to obtain pseudo pixelwise annotations with well boundaries. Then, to reduce the compact of misjudgments in pseudo annotations, we construct a contrastive learning strategy to encourage the features inside ROI as close as possible and separate background features from foreground features. Comprehensive experiments demonstrate the superiority of our proposal. Code is available at https://github.com/HE-Lingfeng/ROI-Extraction
Cross-modal contrastive learning in vision language pretraining (VLP) faces the challenge of (partial) false negatives. In this paper, we study this problem from the perspective of Mutual Information (MI) optimization. It is common sense that InfoNCE loss used in contrastive learning will maximize the lower bound of MI between anchors and their positives, while we theoretically prove that MI involving negatives also matters when noises commonly exist. Guided by a more general lower bound form for optimization, we propose a contrastive learning strategy regulated by progressively refined cross-modal similarity, to more accurately optimize MI between an image/text anchor and its negative texts/images instead of improperly minimizing it. Our method performs competitively on four downstream cross-modal tasks and systematically balances the beneficial and harmful effects of (partial) false negative samples under theoretical guidance.
New roads are being constructed all the time. However, the capabilities of previous deep forecasting models to generalize to new roads not seen in the training data (unseen roads) are rarely explored. In this paper, we introduce a novel setup called a spatio-temporal (ST) split to evaluate the models' capabilities to generalize to unseen roads. In this setup, the models are trained on data from a sample of roads, but tested on roads not seen in the training data. Moreover, we also present a novel framework called Spatial Contrastive Pre-Training (SCPT) where we introduce a spatial encoder module to extract latent features from unseen roads during inference time. This spatial encoder is pre-trained using contrastive learning. During inference, the spatial encoder only requires two days of traffic data on the new roads and does not require any re-training. We also show that the output from the spatial encoder can be used effectively to infer latent node embeddings on unseen roads during inference time. The SCPT framework also incorporates a new layer, named the spatially gated addition (SGA) layer, to effectively combine the latent features from the output of the spatial encoder to existing backbones. Additionally, since there is limited data on the unseen roads, we argue that it is better to decouple traffic signals to trivial-to-capture periodic signals and difficult-to-capture Markovian signals, and for the spatial encoder to only learn the Markovian signals. Finally, we empirically evaluated SCPT using the ST split setup on four real-world datasets. The results showed that adding SCPT to a backbone consistently improves forecasting performance on unseen roads. More importantly, the improvements are greater when forecasting further into the future. The codes are available on GitHub: https://github.com/cruiseresearchgroup/forecasting-on-new-roads .
We introduce a novel Region-based contrastive pretraining for Medical Image Retrieval (RegionMIR) that demonstrates the feasibility of medical image retrieval with similar anatomical regions. RegionMIR addresses two major challenges for medical image retrieval i) standardization of clinically relevant searching criteria (e.g., anatomical, pathology-based), and ii) localization of anatomical area of interests that are semantically meaningful. In this work, we propose an ROI image retrieval image network that retrieves images with similar anatomy by extracting anatomical features (via bounding boxes) and evaluate similarity between pairwise anatomy-categorized features between the query and the database of images using contrastive learning. ROI queries are encoded using a contrastive-pretrained encoder that was fine-tuned for anatomy classification, which generates an anatomical-specific latent space for region-correlated image retrieval. During retrieval, we compare the anatomically encoded query to find similar features within a feature database generated from training samples, and retrieve images with similar regions from training samples. We evaluate our approach on both anatomy classification and image retrieval tasks using the Chest ImaGenome Dataset. Our proposed strategy yields an improvement over state-of-the-art pretraining and co-training strategies, from 92.24 to 94.12 (2.03%) classification accuracy in anatomies. We qualitatively evaluate the image retrieval performance demonstrating generalizability across multiple anatomies with different morphology.
Self-supervised methods based on contrastive learning have achieved great success in unsupervised visual representation learning. However, most methods under this framework suffer from the problem of false negative samples. Inspired by the mean shift for self-supervised learning, we propose a new simple framework, namely Multiple Sample Views and Queues (MSVQ). We jointly construct three soft labels on-the-fly by utilizing two complementary and symmetric approaches: multiple augmented positive views and two momentum encoders that generate various semantic features for negative samples. Two teacher networks perform similarity relationship calculations with negative samples and then transfer this knowledge to the student network. Let the student network mimic the similarity relationships between the samples, thus giving the student network a more flexible ability to identify false negative samples in the dataset. The classification results on four benchmark image datasets demonstrate the high effectiveness and efficiency of our approach compared to some classical methods. Source code and pretrained models are available \href{https://github.com/pc-cp/MSVQ}{here}.
Sequential recommendation (SR) aims to model user preferences by capturing behavior patterns from their item historical interaction data. Most existing methods model user preference in the time domain, omitting the fact that users' behaviors are also influenced by various frequency patterns that are difficult to separate in the entangled chronological items. However, few attempts have been made to train SR in the frequency domain, and it is still unclear how to use the frequency components to learn an appropriate representation for the user. To solve this problem, we shift the viewpoint to the frequency domain and propose a novel Contrastive Enhanced \textbf{SLI}de Filter \textbf{M}ixEr for Sequential \textbf{Rec}ommendation, named \textbf{SLIME4Rec}. Specifically, we design a frequency ramp structure to allow the learnable filter slide on the frequency spectrums across different layers to capture different frequency patterns. Moreover, a Dynamic Frequency Selection (DFS) and a Static Frequency Split (SFS) module are proposed to replace the self-attention module for effectively extracting frequency information in two ways. DFS is used to select helpful frequency components dynamically, and SFS is combined with the dynamic frequency selection module to provide a more fine-grained frequency division. Finally, contrastive learning is utilized to improve the quality of user embedding learned from the frequency domain. Extensive experiments conducted on five widely used benchmark datasets demonstrate our proposed model performs significantly better than the state-of-the-art approaches. Our code is available at https://github.com/sudaada/SLIME4Rec.
In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval either explicitly post-process the raw retrieval results from standard retrieval systems or try to learn multi-vector representations of images to represent their diverse semantics. However, neither of them is good enough to balance relevance and diversity. On the one hand, standard retrieval systems are usually biased to common semantics and seldom exploit diversity-aware regularization in training, which makes it difficult to promote diversity by post-processing. On the other hand, multi-vector representation methods are not guaranteed to learn robust multiple projections. As a result, irrelevant images and images of rare or unique semantics may be projected inappropriately, which degrades the relevance and diversity of the results generated by some typical algorithms like top-k. To cope with these problems, this paper presents a new method called CoLT that tries to generate much more representative and robust representations for accurately classifying images. Specifically, CoLT first extracts semantics-aware image features by enhancing the preliminary representations of an existing one-to-one cross-modal system with semantics-aware contrastive learning. Then, a transformer-based token classifier is developed to subsume all the features into their corresponding categories. Finally, a post-processing algorithm is designed to retrieve images from each category to form the final retrieval result. Extensive experiments on two real-world datasets Div400 and Div150Cred show that CoLT can effectively boost diversity, and outperforms the existing methods as a whole (with a higher F1 score).
Despite the recent advances in open-domain dialogue systems, building a reliable evaluation metric is still a challenging problem. Recent studies proposed learnable metrics based on classification models trained to distinguish the correct response. However, neural classifiers are known to make overly confident predictions for examples from unseen distributions. We propose DEnsity, which evaluates a response by utilizing density estimation on the feature space derived from a neural classifier. Our metric measures how likely a response would appear in the distribution of human conversations. Moreover, to improve the performance of DEnsity, we utilize contrastive learning to further compress the feature space. Experiments on multiple response evaluation datasets show that DEnsity correlates better with human evaluations than the existing metrics. Our code is available at https://github.com/ddehun/DEnsity.
Contrastive opinion extraction aims to extract a structured summary or key points organised as positive and negative viewpoints towards a common aspect or topic. Most recent works for unsupervised key point extraction is largely built on sentence clustering or opinion summarisation based on the popularity of opinions expressed in text. However, these methods tend to generate aspect clusters with incoherent sentences, conflicting viewpoints, redundant aspects. To address these problems, we propose a novel unsupervised Contrastive OpinioN Extraction model, called Cone, which learns disentangled latent aspect and sentiment representations based on pseudo aspect and sentiment labels by combining contrastive learning with iterative aspect/sentiment clustering refinement. Apart from being able to extract contrastive opinions, it is also able to quantify the relative popularity of aspects and their associated sentiment distributions. The model has been evaluated on both a hotel review dataset and a Twitter dataset about COVID vaccines. The results show that despite using no label supervision or aspect-denoted seed words, Cone outperforms a number of competitive baselines on contrastive opinion extraction. The results of Cone can be used to offer a better recommendation of products and services online.
In reinforcement learning, unsupervised skill discovery aims to learn diverse skills without extrinsic rewards. Previous methods discover skills by maximizing the mutual information (MI) between states and skills. However, such an MI objective tends to learn simple and static skills and may hinder exploration. In this paper, we propose a novel unsupervised skill discovery method through contrastive learning among behaviors, which makes the agent produce similar behaviors for the same skill and diverse behaviors for different skills. Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective. Meanwhile, our method implicitly increases the state entropy to obtain better state coverage. We evaluate our method on challenging mazes and continuous control tasks. The results show that our method generates diverse and far-reaching skills, and also obtains competitive performance in downstream tasks compared to the state-of-the-art methods.
Existing methods for video question answering (VideoQA) often suffer from spurious correlations between different modalities, leading to a failure in identifying the dominant visual evidence and the intended question. Moreover, these methods function as black boxes, making it difficult to interpret the visual scene during the QA process. In this paper, to discover critical video segments and frames that serve as the visual causal scene for generating reliable answers, we present a causal analysis of VideoQA and propose a framework for cross-modal causal relational reasoning, named Visual Causal Scene Refinement (VCSR). Particularly, a set of causal front-door intervention operations is introduced to explicitly find the visual causal scenes at both segment and frame levels. Our VCSR involves two essential modules: i) the Question-Guided Refiner (QGR) module, which refines consecutive video frames guided by the question semantics to obtain more representative segment features for causal front-door intervention; ii) the Causal Scene Separator (CSS) module, which discovers a collection of visual causal and non-causal scenes based on the visual-linguistic causal relevance and estimates the causal effect of the scene-separating intervention in a contrastive learning manner. Extensive experiments on the NExT-QA, Causal-VidQA, and MSRVTT-QA datasets demonstrate the superiority of our VCSR in discovering visual causal scene and achieving robust video question answering. The code is available at https://github.com/YangLiu9208/VCSR.
Learning from noisy data has attracted much attention, where most methods focus on closed-set label noise. However, a more common scenario in the real world is the presence of both open-set and closed-set noise. Existing methods typically identify and handle these two types of label noise separately by designing a specific strategy for each type. However, in many real-world scenarios, it would be challenging to identify open-set examples, especially when the dataset has been severely corrupted. Unlike the previous works, we explore how models behave when faced with open-set examples, and find that \emph{a part of open-set examples gradually get integrated into certain known classes}, which is beneficial for the separation among known classes. Motivated by the phenomenon, we propose a novel two-step contrastive learning method CECL (Class Expansion Contrastive Learning) which aims to deal with both types of label noise by exploiting the useful information of open-set examples. Specifically, we incorporate some open-set examples into closed-set classes to enhance performance while treating others as delimiters to improve representative ability. Extensive experiments on synthetic and real-world datasets with diverse label noise demonstrate the effectiveness of CECL.