Deep hashing approaches, including deep quantization and deep binary hashing, have become a common solution to large-scale image retrieval due to high computation and storage efficiency. Most existing hashing methods can not produce satisfactory resu
lts for fine-grained retrieval, because they usually adopt the outputs of the last CNN layer to generate binary codes, which is less effective to capture subtle but discriminative visual details. To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ). Specifically, we propose a Pyramid Hybrid Pooling (PHP) module to capture and preserve fine-grained semantic information from multi-level features. Besides, we propose a learnable quantization module with a partial attention mechanism, which helps to optimize the most relevant codewords and improves the quantization. Comprehensive experiments demonstrate that PHPQ outperforms state-of-the-art methods.
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems. To alleviate the reliance on expensive annotations, unsupervised deep hashing becomes an impo
rtant research problem. This paper provides a novel solution to unsupervised deep quantization, namely Contrastive Quantization with Code Memory (MeCoQ). Different from existing reconstruction-based strategies, we learn unsupervised binary descriptors by contrastive learning, which can better capture discriminative visual semantics. Besides, we uncover that codeword diversity regularization is critical to prevent contrastive learning-based quantization from model degeneration. Moreover, we introduce a novel quantization code memory module that boosts contrastive learning with lower feature drift than conventional feature memories. Extensive experiments on benchmark datasets show that MeCoQ outperforms state-of-the-art methods.
Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself. However, some of the current methods tend to cheat from the background, i.e., the p
rediction is highly dependent on the video background instead of the motion, making the model vulnerable to background changes. To mitigate the model reliance towards the background, we propose to remove the background impact by adding the background. That is, given a video, we randomly select a static frame and add it to every other frames to construct a distracting video sample. Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes. We term our method as emph{Background Erasing} (BE). It is worth noting that the implementation of our method is so simple and neat and can be added to most of the SOTA methods without much efforts. Specifically, BE brings 16.4% and 19.1% improvements with MoCo on the severely biased datasets UCF101 and HMDB51, and 14.5% improvement on the less biased dataset Diving48.
One significant factor we expect the video representation learning to capture, especially in contrast with the image representation learning, is the object motion. However, we found that in the current mainstream video datasets, some action categorie
s are highly related with the scene where the action happens, making the model tend to degrade to a solution where only the scene information is encoded. For example, a trained model may predict a video as playing football simply because it sees the field, neglecting that the subject is dancing as a cheerleader on the field. This is against our original intention towards the video representation learning and may bring scene bias on different dataset that can not be ignored. In order to tackle this problem, we propose to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid. Specifically, we construct a positive clip and a negative clip for each video. Compared to the original video, the positive/negative is motion-untouched/broken but scene-broken/untouched by Spatial Local Disturbance and Temporal Local Disturbance. Our objective is to pull the positive closer while pushing the negative farther to the original clip in the latent space. In this way, the impact of the scene is weakened while the temporal sensitivity of the network is further enhanced. We conduct experiments on two tasks with various backbones and different pre-training datasets, and find that our method surpass the SOTA methods with a remarkable 8.1% and 8.8% improvement towards action recognition task on the UCF101 and HMDB51 datasets respectively using the same backbone.
Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper proposes
a novel Video-based Temporal-Discriminative Learning (VTDL) framework in self-supervised manner. Without labelled data for network pretraining, temporal triplet is generated for each anchor video by using segment of the same or different time interval so as to enhance the capacity for temporal feature representation. Measuring temporal information by time derivative, Temporal Consistent Augmentation (TCA) is designed to ensure that the time derivative (in any order) of the augmented positive is invariant except for a scaling constant. Finally, temporal-discriminative features are learnt by minimizing the distance between each anchor and its augmented positive, while the distance between each anchor and its augmented negative as well as other videos saved in the memory bank is maximized to enrich the representation diversity. In the downstream action recognition task, the proposed method significantly outperforms existing related works. Surprisingly, the proposed self-supervised approach is better than fully-supervised methods on UCF101 and HMDB51 when a small-scale video dataset (with only thousands of videos) is used for pre-training. The code has been made publicly available on https://github.com/FingerRec/Self-Supervised-Temporal-Discriminative-Representation-Learning-for-Video-Action-Recognition.
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a novel way t
o obtain the surrogate supervision signal based on high-level feature maps under consistency regularization. In this paper, we propose a Spatio-Temporal Consistency Regularization between different output features generated from a siamese network including a clean path fed with original video and a noise path fed with the corresponding augmented video. Based on the Spatio-Temporal characteristics of video, we develop two video-based data augmentation methods, i.e., Spatio-Temporal Transformation and Intra-Video Mixup. Consistency of the former one is proposed to model transformation consistency of features, while the latter one aims at retaining spatial invariance to extract action-related features. Extensive experiments demonstrate that our method achieves substantial improvements compared with state-of-the-art self-supervised learning methods for action recognition. When using our method as an additional regularization term and combine with current surrogate supervision signals, we achieve 22% relative improvement over the previous state-of-the-art on HMDB51 and 7% on UCF101.
Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. However, the latent entity type
information in the immediate context of the mention is neglected, which causes the models often link mentions to incorrect entities with incorrect type. To tackle this problem, we propose to inject latent entity type information into the entity embeddings based on pre-trained BERT. In addition, we integrate a BERT-based entity similarity score into the local context model of a state-of-the-art model to better capture latent entity type information. Our model significantly outperforms the state-of-the-art entity linking models on standard benchmark (AIDA-CoNLL). Detailed experiment analysis demonstrates that our model corrects most of the type errors produced by the direct baseline.
Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consi
stent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.
Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts. However, large proportions of generated texts do not actually conform to the input data. To address this issue, we propo
se a new training framework which attempts to verify the consistency between the generated texts and the input data to guide the training process. To measure the consistency, a relation extraction model is applied to check information overlaps between the input data and the generated texts. The non-differentiable consistency signal is optimized via reinforcement learning. Experimental results on a recently released challenging dataset ROTOWIRE show improvements from our framework in various metrics.
