We propose a self-supervised method to learn feature representations from videos. A standard approach in traditional self-supervised methods uses positive-negative data pairs to train with contrastive learning strategy. In such a case, different modalities of the same video are treated as positives and video clips from a different video are treated as negatives. Because the spatio-temporal information is important for video representation, we extend the negative samples by introducing intra-negative samples, which are transformed from the same anchor video by breaking temporal relations in video clips. With the proposed Inter-Intra Contrastive (IIC) framework, we can train spatio-temporal convolutional networks to learn video representations. There are many flexible options in our IIC framework and we conduct experiments by using several different configurations. Evaluations are conducted on video retrieval and video recognition tasks using the learned video representation. Our proposed IIC outperforms current state-of-the-art results by a large margin, such as 16.7% and 9.5% points improvements in top-1 accuracy on UCF101 and HMDB51 datasets for video retrieval, respectively. For video recognition, improvements can also be obtained on these two benchmark datasets. Code is available at https://github.com/BestJuly/Inter-intra-video-contrastive-learning.
The spread of social networking services has created an increasing demand for selecting, editing, and generating impressive images. This trend increases the importance of evaluating image aesthetics as a complementary function of automatic image processing. We propose a multi-patch method, named MPA-Net (Multi-Patch Aggregation Network), to predict image aesthetics scores by maintaining the original aspect ratios of contents in the images. Through an experiment involving the large-scale AVA dataset, which contains 250,000 images, we show that the effectiveness of the equal-interval multi-patch selection approach for aesthetics score prediction is significant compared to the single-patch prediction and random patch selection approaches. For this dataset, MPA-Net outperforms the neural image assessment algorithm, which was regarded as a baseline method. In particular, MPA-Net yields a 0.073 (11.5%) higher linear correlation coefficient (LCC) of aesthetics scores and a 0.088 (14.4%) higher Spearman's rank correlation coefficient (SRCC). MPA-Net also reduces the mean square error (MSE) by 0.0115 (4.18%) and achieves results for the LCC and SRCC that are comparable to those of the state-of-the-art continuous aesthetics score prediction methods. Most notably, MPA-Net yields a significant lower MSE especially for images with aspect ratios far from 1.0, indicating that MPA-Net is useful for a wide range of image aspect ratios. MPA-Net uses only images and does not require external information during the training nor prediction stages. Therefore, MPA-Net has great potential for applications aside from aesthetics score prediction such as other human subjectivity prediction.
Recently, 3D convolutional networks (3D ConvNets) yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets. By replacing traditional stacked RGB frames with residual ones, 35.6% and 26.6% points improvements over top-1 accuracy can be obtained on the UCF101 and HMDB51 datasets when ResNet-18 models are trained from scratch. And we achieved the state-of-the-art results in this training mode. Analysis shows that better motion features can be extracted using residual frames compared to RGB counterpart. By combining with a simple appearance path, our proposal can be even better than some methods using optical flow streams.
In this paper, we study the generalization properties of neural networks under input perturbations and show that minimal training data corruption by a few pixel modifications can cause drastic overfitting. We propose an evolutionary algorithm to search for optimal pixel perturbations using novel cost function inspired from literature in domain adaptation that explicitly maximizes the generalization gap and domain divergence between clean and corrupted images. Our method outperforms previous pixel-based data distribution shift methods on state-of-the-art Convolutional Neural Networks (CNNs) architectures. Interestingly, we find that the choice of optimization plays an important role in generalization robustness due to the empirical observation that SGD is resilient to such training data corruption unlike adaptive optimization techniques (ADAM). Our source code is available at https://github.com/subhajitchaudhury/evo-shift.
Background and Objective: Object detection is a primary research interest in computer vision. Sperm-cell detection in a densely populated bull semen microscopic observation video presents challenges such as partial occlusion, vast number of objects in a single video frame, tiny size of the object, artifacts, low contrast, and blurry objects because of the rapid movement of the sperm cells. This study proposes an architecture, called DeepSperm, that solves the aforementioned challenges and is more accurate and faster than state-of-the-art architectures. Methods: In the proposed architecture, we use only one detection layer, which is specific for small object detection. For handling overfitting and increasing accuracy, we set a higher network resolution, use a dropout layer, and perform data augmentation on hue, saturation, and exposure. Several hyper-parameters are tuned to achieve better performance. We compare our proposed method with those of a conventional image processing-based object-detection method, you only look once (YOLOv3), and mask region-based convolutional neural network (Mask R-CNN). Results: In our experiment, we achieve 86.91 mAP on the test dataset and a processing speed of 50.3 fps. In comparison with YOLOv3, we achieve an increase of 16.66 mAP point, 3.26 x faster on testing, and 1.4 x faster on training with a small training dataset, which contains 40 video frames. The weights file size was also reduced significantly, with 16.94 x smaller than that of YOLOv3. Moreover, it requires 1.3 x less graphical processing unit (GPU) memory than YOLOv3. Conclusions: This study proposes DeepSperm, which is a simple, effective, and efficient architecture with its hyper-parameters and configuration to detect bull sperm cells robustly in real time. In our experiment, we surpass the state of the art in terms of accuracy, speed, and resource needs.
Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way to extract motion features from videos utilizing residual frames as the input data in 3D ConvNets. By replacing traditional stacked RGB frames with residual ones, 20.5% and 12.5% points improvements over top-1 accuracy can be achieved on the UCF101 and HMDB51 datasets when trained from scratch. Because residual frames contain little information of object appearance, we further use a 2D convolutional network to extract appearance features and combine them with the results from residual frames to form a two-path solution. In three benchmark datasets, our two-path solution achieved better or comparable performances than those using additional optical flow methods, especially outperformed the state-of-the-art models on Mini-kinetics dataset. Further analysis indicates that better motion features can be extracted using residual frames with 3D ConvNets, and our residual-frame-input path is a good supplement for existing RGB-frame-input models.
This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology. Although deep learning methods have been attempted to get dermatologist level accuracy in several individual conditions, it has not been rigorously tested for common clinical complaints. Most projects involve data acquired in well-controlled laboratory conditions. This may not reflect regular clinical evaluation where corresponding image quality is not always ideal. We test the robustness of deep learning methods by simulating non-ideal characteristics on user submitted images of ten classes of diseases. Assessing via imitated conditions, we have found the overall accuracy to drop and individual predictions change significantly in many cases despite of robust training.
Conventional video summarization approaches based on reinforcement learning have the problem that the reward can only be received after the whole summary is generated. Such kind of reward is sparse and it makes reinforcement learning hard to converge. Another problem is that labelling each frame is tedious and costly, which usually prohibits the construction of large-scale datasets. To solve these problems, we propose a weakly supervised hierarchical reinforcement learning framework, which decomposes the whole task into several subtasks to enhance the summarization quality. This framework consists of a manager network and a worker network. For each subtask, the manager is trained to set a subgoal only by a task-level binary label, which requires much fewer labels than conventional approaches. With the guide of the subgoal, the worker predicts the importance scores for video frames in the subtask by policy gradient according to both global reward and innovative defined sub-rewards to overcome the sparse problem. Experiments on two benchmark datasets show that our proposal has achieved the best performance, even better than supervised approaches.
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. Our method is based on generative adversarial networks (GANs), but instead of simply generating images with a neural network, we enhance images utilizing image editing software such as Adobe Photoshop for the following three benefits: enhanced images have no artifacts, the same enhancement can be applied to larger images, and the enhancement is interpretable. To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools the discriminator. Our framework can use high-quality non-differentiable filters present in image editing software, which enables image enhancement with high performance. We apply the proposed method to two unpaired image enhancement tasks: photo enhancement and face beautification. Our experimental results demonstrate that the proposed method achieves better performance, compared to the performances of the state-of-the-art methods based on unpaired learning.