We address the problem of devising the means for a robot to rapidly and safely learn insertion skills with just a few human interventions and without hand-crafted rewards or demonstrations. Our InsertionNet version 2.0 provides an improved technique to robustly cope with a wide range of use-cases featuring different shapes, colors, initial poses, etc. In particular, we present a regression-based method based on multimodal input from stereo perception and force, augmented with contrastive learning for the efficient learning of valuable features. In addition, we introduce a one-shot learning technique for insertion, which relies on a relation network scheme to better exploit the collected data and to support multi-step insertion tasks. Our method improves on the results obtained with the original InsertionNet, achieving an almost perfect score (above 97.5$\%$ on 200 trials) in 16 real-life insertion tasks while minimizing the execution time and contact during insertion. We further demonstrate our method's ability to tackle a real-life 3-step insertion task and perfectly solve an unseen insertion task without learning.
Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds. Self-supervised learning, which operates without any human labeling, is a promising approach to address this issue. We observe in the real world that humans are capable of mapping the visual concepts learnt from 2D images to understand the 3D world. Encouraged by this insight, we propose CrossPoint, a simple cross-modal contrastive learning approach to learn transferable 3D point cloud representations. It enables a 3D-2D correspondence of objects by maximizing agreement between point clouds and the corresponding rendered 2D image in the invariant space, while encouraging invariance to transformations in the point cloud modality. Our joint training objective combines the feature correspondences within and across modalities, thus ensembles a rich learning signal from both 3D point cloud and 2D image modalities in a self-supervised fashion. Experimental results show that our approach outperforms the previous unsupervised learning methods on a diverse range of downstream tasks including 3D object classification and segmentation. Further, the ablation studies validate the potency of our approach for a better point cloud understanding. Code and pretrained models are available at http://github.com/MohamedAfham/CrossPoint.
Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose a simple, effective, and practical method, termed as UFCL, to alleviate the gap. Three key issues are concerned and improved: First, we introduce a robust and powerful backbone, ResNet50-IBN, which has an ability of domain adaptation when we transfer ImageNet pre-trained models to FGVC tasks. Next, we propose to introduce HDBSCAN instead of DBSCAN to do clustering, which can generate better clusters for adjacent categories with fewer hyper-parameters. Finally, we propose a weighted feature agent and its updating mechanism to do contrastive learning by using the pseudo labels with inevitable noise, which can improve the optimization process of learning the parameters of the network. The effectiveness of our UFCL is verified on CUB-200-2011, Oxford-Flowers, Oxford-Pets, Stanford-Dogs, Stanford-Cars and FGVC-Aircraft datasets. Under the unsupervised FGVC setting, we achieve state-of-the-art results, and analyze the key factors and the important parameters to provide a practical guidance.
Robotic detection of people in crowded and/or cluttered human-centered environments including hospitals, long-term care, stores and airports is challenging as people can become occluded by other people or objects, and deform due to variations in clothing or pose. There can also be loss of discriminative visual features due to poor lighting. In this paper, we present a novel multimodal person detection architecture to address the mobile robot problem of person detection under intraclass variations. We present a two-stage training approach using 1) a unique pretraining method we define as Temporal Invariant Multimodal Contrastive Learning (TimCLR), and 2) a Multimodal Faster R-CNN (MFRCNN) detector. TimCLR learns person representations that are invariant under intraclass variations through unsupervised learning. Our approach is unique in that it generates image pairs from natural variations within multimodal image sequences, in addition to synthetic data augmentation, and contrasts crossmodal features to transfer invariances between different modalities. These pretrained features are used by the MFRCNN detector for finetuning and person detection from RGB-D images. Extensive experiments validate the performance of our DL architecture in both human-centered crowded and cluttered environments. Results show that our method outperforms existing unimodal and multimodal person detection approaches in terms of detection accuracy in detecting people with body occlusions and pose deformations in different lighting conditions.
In this paper, we propose an augmentation-free graph contrastive learning framework, namely ACTIVE, to solve the problem of partial multi-view clustering. Notably, we suppose that the representations of similar samples (i.e., belonging to the same cluster) and their multiply views features should be similar. This is distinct from the general unsupervised contrastive learning that assumes an image and its augmentations share a similar representation. Specifically, relation graphs are constructed using the nearest neighbours to identify existing similar samples, then the constructed inter-instance relation graphs are transferred to the missing views to build graphs on the corresponding missing data. Subsequently, two main components, within-view graph contrastive learning (WGC) and cross-view graph consistency learning (CGC), are devised to maximize the mutual information of different views within a cluster. The proposed approach elevates instance-level contrastive learning and missing data inference to the cluster-level, effectively mitigating the impact of individual missing data on clustering. Experiments on several challenging datasets demonstrate the superiority of our proposed methods.
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pixels that uses discrete world models to represent latent states with categorical variables. Dreaming is also a form of reinforcement learning from pixels that attempts to avoid the autoencoding process in general world model training by involving a reconstruction-free contrastive learning objective. The proposed DreamingV2 is a novel approach of adopting both the discrete representation of DreamingV2 and the reconstruction-free objective of Dreaming. Compared to DreamerV2 and other recent model-based methods without reconstruction, DreamingV2 achieves the best scores on five simulated challenging 3D robot arm tasks. We believe that DreamingV2 will be a reliable solution for robot learning since its discrete representation is suitable to describe discontinuous environments, and the reconstruction-free fashion well manages complex vision observations.
Logical reasoning is of vital importance to natural language understanding. Previous studies either employ graph-based models to incorporate prior knowledge about logical relations, or introduce symbolic logic into neural models through data augmentation. These methods, however, heavily depend on annotated training data, and thus suffer from over-fitting and poor generalization problems due to the dataset sparsity. To address these two problems, in this paper, we propose MERIt, a MEta-path guided contrastive learning method for logical ReasonIng of text, to perform self-supervised pre-training on abundant unlabeled text data. Two novel strategies serve as indispensable components of our method. In particular, a strategy based on meta-path is devised to discover the logical structure in natural texts, followed by a counterfactual data augmentation strategy to eliminate the information shortcut induced by pre-training. The experimental results on two challenging logical reasoning benchmarks, i.e., ReClor and LogiQA, demonstrate that our method outperforms the SOTA baselines with significant improvements.
The lack of labeled data is a major obstacle to learning high-quality sentence embeddings. Recently, self-supervised contrastive learning (SCL) is regarded as a promising way to address this problem. However, the existing works mainly rely on hand-crafted data annotation heuristics to generate positive training samples, which not only call for domain expertise and laborious tuning, but are also prone to the following unfavorable cases: 1) trivial positives, 2) coarse-grained positives, and 3) false positives. As a result, the self-supervision's quality can be severely limited in reality. In this work, we propose a novel framework InfoCSE to address the above problems. Instead of relying on annotation heuristics defined by humans, it leverages the sentence representation model itself and realizes the following iterative self-supervision process: on one hand, the improvement of sentence representation may contribute to the quality of data annotation; on the other hand, more effective data annotation helps to generate high-quality positive samples, which will further improve the current sentence representation model. In other words, the representation learning and data annotation become mutually reinforced, where a strong self-supervision effect can be derived. Extensive experiments are performed based on three benchmark datasets, where notable improvements can be achieved against the existing SCL-based methods.
Contrastive learning is emerging as a powerful technique for extracting knowledge from unlabeled data. This technique requires a balanced mixture of two ingredients: positive (similar) and negative (dissimilar) samples. This is typically achieved by maintaining a queue of negative samples during training. Prior works in the area typically uses a fixed-length negative sample queue, but how the negative sample size affects the model performance remains unclear. The opaque impact of the number of negative samples on performance when employing contrastive learning aroused our in-depth exploration. This paper presents a momentum contrastive learning model with negative sample queue for sentence embedding, namely MoCoSE. We add the prediction layer to the online branch to make the model asymmetric and together with EMA update mechanism of the target branch to prevent the model from collapsing. We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples. Our experiments find that the best results are obtained when the maximum traceable distance is at a certain range, demonstrating that there is an optimal range of historical information for a negative sample queue. We evaluate the proposed unsupervised MoCoSE on the semantic text similarity (STS) task and obtain an average Spearman's correlation of $77.27\%$. Source code is available at https://github.com/xbdxwyh/mocose.
Modeling user's long-term and short-term interests is crucial for accurate recommendation. However, since there is no manually annotated label for user interests, existing approaches always follow the paradigm of entangling these two aspects, which may lead to inferior recommendation accuracy and interpretability. In this paper, to address it, we propose a Contrastive learning framework to disentangle Long and Short-term interests for Recommendation (CLSR) with self-supervision. Specifically, we first propose two separate encoders to independently capture user interests of different time scales. We then extract long-term and short-term interests proxies from the interaction sequences, which serve as pseudo labels for user interests. Then pairwise contrastive tasks are designed to supervise the similarity between interest representations and their corresponding interest proxies. Finally, since the importance of long-term and short-term interests is dynamically changing, we propose to adaptively aggregate them through an attention-based network for prediction. We conduct experiments on two large-scale real-world datasets for e-commerce and short-video recommendation. Empirical results show that our CLSR consistently outperforms all state-of-the-art models with significant improvements: GAUC is improved by over 0.01, and NDCG is improved by over 4%. Further counterfactual evaluations demonstrate that stronger disentanglement of long and short-term interests is successfully achieved by CLSR. The code and data are available at https://github.com/tsinghua-fib-lab/CLSR.
Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks. This paper proposes a multi-level contrastive learning (ML-CTL) framework to further improve the cross-lingual ability of pre-trained models. The proposed method uses translated parallel data to encourage the model to generate similar semantic embeddings for different languages. However, unlike the sentence-level alignment used in most previous studies, in this paper, we explicitly integrate the word-level information of each pair of parallel sentences into contrastive learning. Moreover, cross-zero noise contrastive estimation (CZ-NCE) loss is proposed to alleviate the impact of the floating-point error in the training process with a small batch size. The proposed method significantly improves the cross-lingual transfer ability of our basic model (mBERT) and outperforms on multiple zero-shot cross-lingual downstream tasks compared to the same-size models in the Xtreme benchmark.
We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning. Specifically, our proposed metric may be interpreted as a dependence measure between two adapted projections learned from the so-called latent representations. This is in contrast to the cosine similarity measure in the conventional contrastive learning model, which accounts for correlation information. To the best of our knowledge, this effectively non-linearly fused information embedded in the Jaccard similarity, is novel to self-supervision learning with promising results. The proposed approach is compared to two state-of-the-art self-supervised contrastive learning methods on three image datasets. We not only demonstrate its amenable applicability in current ML problems, but also its improved performance and training efficiency.
High-quality phrase representations are essential to finding topics and related terms in documents (a.k.a. topic mining). Existing phrase representation learning methods either simply combine unigram representations in a context-free manner or rely on extensive annotations to learn context-aware knowledge. In this paper, we propose UCTopic, a novel unsupervised contrastive learning framework for context-aware phrase representations and topic mining. UCTopic is pretrained in a large scale to distinguish if the contexts of two phrase mentions have the same semantics. The key to pretraining is positive pair construction from our phrase-oriented assumptions. However, we find traditional in-batch negatives cause performance decay when finetuning on a dataset with small topic numbers. Hence, we propose cluster-assisted contrastive learning(CCL) which largely reduces noisy negatives by selecting negatives from clusters and further improves phrase representations for topics accordingly. UCTopic outperforms the state-of-the-art phrase representation model by 38.2% NMI in average on four entity cluster-ing tasks. Comprehensive evaluation on topic mining shows that UCTopic can extract coherent and diverse topical phrases.
Distant supervision assumes that any sentence containing the same entity pairs reflects identical relationships. Previous works of distantly supervised relation extraction (DSRE) task generally focus on sentence-level or bag-level de-noising techniques independently, neglecting the explicit interaction with cross levels. In this paper, we propose a hierarchical contrastive learning Framework for Distantly Supervised relation extraction (HiCLRE) to reduce noisy sentences, which integrate the global structural information and local fine-grained interaction. Specifically, we propose a three-level hierarchical learning framework to interact with cross levels, generating the de-noising context-aware representations via adapting the existing multi-head self-attention, named Multi-Granularity Recontextualization. Meanwhile, pseudo positive samples are also provided in the specific level for contrastive learning via a dynamic gradient-based data augmentation strategy, named Dynamic Gradient Adversarial Perturbation. Experiments demonstrate that HiCLRE significantly outperforms strong baselines in various mainstream DSRE datasets.
Recently, finetuning a pretrained language model to capture the similarity between sentence embeddings has shown the state-of-the-art performance on the semantic textual similarity (STS) task. However, the absence of an interpretation method for the sentence similarity makes it difficult to explain the model output. In this work, we explicitly describe the sentence distance as the weighted sum of contextualized token distances on the basis of a transportation problem, and then present the optimal transport-based distance measure, named RCMD; it identifies and leverages semantically-aligned token pairs. In the end, we propose CLRCMD, a contrastive learning framework that optimizes RCMD of sentence pairs, which enhances the quality of sentence similarity and their interpretation. Extensive experiments demonstrate that our learning framework outperforms other baselines on both STS and interpretable-STS benchmarks, indicating that it computes effective sentence similarity and also provides interpretation consistent with human judgement. The code and checkpoint are publicly available at https://github.com/sh0416/clrcmd.
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically explain the success of contrastive learning on downstream classification tasks prove guarantees depending on properties of {\em augmentations} and the value of {\em contrastive loss} of representations. We demonstrate that such analyses, that ignore {\em inductive biases} of the function class and training algorithm, cannot adequately explain the success of contrastive learning, even {\em provably} leading to vacuous guarantees in some settings. Extensive experiments on image and text domains highlight the ubiquity of this problem -- different function classes and algorithms behave very differently on downstream tasks, despite having the same augmentations and contrastive losses. Theoretical analysis is presented for the class of linear representations, where incorporating inductive biases of the function class allows contrastive learning to work with less stringent conditions compared to prior analyses.
Maintaining proper form while exercising is important for preventing injuries and maximizing muscle mass gains. Detecting errors in workout form naturally requires estimating human's body pose. However, off-the-shelf pose estimators struggle to perform well on the videos recorded in gym scenarios due to factors such as camera angles, occlusion from gym equipment, illumination, and clothing. To aggravate the problem, the errors to be detected in the workouts are very subtle. To that end, we propose to learn exercise-oriented image and video representations from unlabeled samples such that a small dataset annotated by experts suffices for supervised error detection. In particular, our domain knowledge-informed self-supervised approaches (pose contrastive learning and motion disentangling) exploit the harmonic motion of the exercise actions, and capitalize on the large variances in camera angles, clothes, and illumination to learn powerful representations. To facilitate our self-supervised pretraining, and supervised finetuning, we curated a new exercise dataset, \emph{Fitness-AQA} (\url{https://github.com/ParitoshParmar/Fitness-AQA}), comprising of three exercises: BackSquat, BarbellRow, and OverheadPress. It has been annotated by expert trainers for multiple crucial and typically occurring exercise errors. Experimental results show that our self-supervised representations outperform off-the-shelf 2D- and 3D-pose estimators and several other baselines. We also show that our approaches can be applied to other domains/tasks such as pose estimation and dive quality assessment.
Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust to tiny input perturbations known as adversarial examples. First we illustrate how to generate valid adversarial images that can easily cause incorrect image attribution. Then we describe an approach to prevent imperceptible adversarial attacks on deep visual fingerprinting models, via robust contrastive learning. The proposed training procedure leverages training on $\ell_\infty$-bounded adversarial examples, it is conceptually simple and incurs only a small computational overhead. The resulting models are substantially more robust, are accurate even on unperturbed images, and perform well even over a database with millions of images. In particular, we achieve 91.6% standard and 85.1% adversarial recall under $\ell_\infty$-bounded perturbations on manipulated images compared to 80.1% and 0.0% from prior work. We also show that robustness generalizes to other types of imperceptible perturbations unseen during training. Finally, we show how to train an adversarially robust image comparator model for detecting editorial changes in matched images.
In this paper, we study contrastive learning from an optimization perspective, aiming to analyze and address a fundamental issue of existing contrastive learning methods that either rely on a large batch size or a large dictionary of feature vectors. We consider a global objective for contrastive learning, which contrasts each positive pair with all negative pairs for an anchor point. From the optimization perspective, we explain why existing methods such as SimCLR require a large batch size in order to achieve a satisfactory result. In order to remove such requirement, we propose a memory-efficient Stochastic Optimization algorithm for solving the Global objective of Contrastive Learning of Representations, named SogCLR. We show that its optimization error is negligible under a reasonable condition after a sufficient number of iterations or is diminishing for a slightly different global contrastive objective. Empirically, we demonstrate that SogCLR with small batch size (e.g., 256) can achieve similar performance as SimCLR with large batch size (e.g., 8192) on self-supervised learning task on ImageNet-1K. We also attempt to show that the proposed optimization technique is generic and can be applied to solving other contrastive losses, e.g., two-way contrastive losses for bimodal contrastive learning. The proposed method is implemented in our open-sourced library LibAUC (www.libauc.org).
Unmanned aerial vehicles (UAVs) are widely used due to their low cost and versatility, but they also pose security and privacy threats. Therefore, reliable detection for low-altitude UAVs is an important issue. The strong ground clutter makes the radar echoes from small UAVs submerged in noise, resulting in low radar detection reliability. A low-altitude UAV detection method based on deep contrastive learning is proposed to address the above problems: Concretely, a low-altitude UAV radar echo model under low-altitude clutter interference is first established. Based on the echo components and the UAV Doppler domain identifiable mechanism, a time-frequency transformation method combining ZAM transform and morphological operations is used to suppress the ambiguity problem under clutter. Then feature extraction and fusion method introducing contrast learning is utilized to suppress non-target ground clutter interference. Finally, a detector relying on semantic features is designed for the reliable identification of low-altitude UAVs. The experiments carried out on both real and simulated data confirm that the proposed method can effectively suppress ground clutter and reliably extract recognizable semantic features of UAVs. The proposed method achieves lower false and missing alarms compared with recent state-of-art solutions and improves the detection accuracy by more than 5% for the same signal-to-noise ratio, which effectively improves the detection reliability.