Program synthesis or code generation aims to generate a program that satisfies a problem specification. Recent approaches using large-scale pretrained language models (LMs) have shown promising results, yet they have some critical limitations. In particular, they often follow a standard supervised fine-tuning procedure to train a code generation model only from the pairs of natural-language problem descriptions and ground-truth programs. Such paradigm largely ignores some important but potentially useful signals in the problem specification such as unit tests, which thus often results in poor performance when solving complex unseen coding tasks. To address the limitations, we propose "CodeRL", a new framework for program synthesis tasks through pretrained LMs and deep reinforcement learning (RL). Specifically, during training, we treat the code-generating LM as an actor network, and introduce a critic network that is trained to predict the functional correctness of generated programs and provide dense feedback signals to the actor. During inference, we introduce a new generation procedure with a critical sampling strategy that allows a model to automatically regenerate programs based on feedback from example unit tests and critic scores. For the model backbones, we extended the encoder-decoder architecture of CodeT5 with enhanced learning objectives, larger model sizes, and better pretraining data. Our method not only achieves new SOTA results on the challenging APPS benchmark, but also shows strong zero-shot transfer capability with new SOTA results on the simpler MBPP benchmark.
Currently, orthogonal time frequency space (OTFS) modulation has drawn much attention to reliable communications in high-mobility scenarios. This paper proposes a doubly-iterative sparsified minimum mean square error (DI-S-MMSE) turbo equalizer, which iteratively exchanges the extrinsic information between a soft-input-soft-input (SISO) MMSE estimator and a SISO decoder. Our proposed equalizer does not suffer from short loops and approaches the performance of the near-optimal symbol-wise maximum a posteriori (MAP) algorithm. To exploit the inherent sparsity of OTFS system, we resort to graph theory to investigate the sparsity pattern of the channel matrix, and propose two sparsification guidelines to reduce the complexity of calculating the matrix inverse at the MMSE estimator. Then, we apply two iterative algorithms to MMSE estimation, i.e., the Generalized Minimal Residual (GMRES) and Factorized Sparse Approximate Inverse (FSPAI) algorithms. The former is used at the initial turbo iteration, whose global convergence is proven in our equalizer, while the latter is used at the subsequent turbo iterations with the help of our proposed guidelines. Simulation results demonstrate that our equalizer has a linear order of complexity while the performance loss incurred by the sparsification is only 0.2 dB at $10^{-4}$ bit error rate. Simulation codes are available to reproduce the results presented in this paper: https://github.com/Alga53/DISMMSE-Turbo-Equalizer-for-OTFS.
End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality differences between speech outputs from the encoder and text inputs to the decoder. In this work, we aim to bridge the modality gap between speech and text to improve translation quality. We propose M-Adapter, a novel Transformer-based module, to adapt speech representations to text. While shrinking the speech sequence, M-Adapter produces features desired for speech-to-text translation via modelling global and local dependencies of a speech sequence. Our experimental results show that our model outperforms a strong baseline by up to 1 BLEU score on the Must-C En$\rightarrow$DE dataset.\footnote{Our code is available at https://github.com/mingzi151/w2v2-st.}
Cross-modal representation learning has become a new normal for bridging the semantic gap between text and visual data. Learning modality agnostic representations in a continuous latent space, however, is often treated as a black-box data-driven training process. It is well-known that the effectiveness of representation learning depends heavily on the quality and scale of training data. For video representation learning, having a complete set of labels that annotate the full spectrum of video content for training is highly difficult if not impossible. These issues, black-box training and dataset bias, make representation learning practically challenging to be deployed for video understanding due to unexplainable and unpredictable results. In this paper, we propose two novel training objectives, likelihood and unlikelihood functions, to unroll semantics behind embeddings while addressing the label sparsity problem in training. The likelihood training aims to interpret semantics of embeddings beyond training labels, while the unlikelihood training leverages prior knowledge for regularization to ensure semantically coherent interpretation. With both training objectives, a new encoder-decoder network, which learns interpretable cross-modal representation, is proposed for ad-hoc video search. Extensive experiments on TRECVid and MSR-VTT datasets show the proposed network outperforms several state-of-the-art retrieval models with a statistically significant performance margin.
Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in various image generation tasks compared with Generative Adversarial Nets (GANs). Recent work on semantic image synthesis mainly follows the \emph{de facto} GAN-based approaches, which may lead to unsatisfactory quality or diversity of generated images. In this paper, we propose a novel framework based on DDPM for semantic image synthesis. Unlike previous conditional diffusion model directly feeds the semantic layout and noisy image as input to a U-Net structure, which may not fully leverage the information in the input semantic mask, our framework processes semantic layout and noisy image differently. It feeds noisy image to the encoder of the U-Net structure while the semantic layout to the decoder by multi-layer spatially-adaptive normalization operators. To further improve the generation quality and semantic interpretability in semantic image synthesis, we introduce the classifier-free guidance sampling strategy, which acknowledge the scores of an unconditional model for sampling process. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed method, achieving state-of-the-art performance in terms of fidelity (FID) and diversity (LPIPS).
Safety is still the main issue of autonomous driving, and in order to be globally deployed, they need to predict pedestrians' motions sufficiently in advance. While there is a lot of research on coarse-grained (human center prediction) and fine-grained predictions (human body keypoints prediction), we focus on 3D bounding boxes, which are reasonable estimates of humans without modeling complex motion details for autonomous vehicles. This gives the flexibility to predict in longer horizons in real-world settings. We suggest this new problem and present a simple yet effective model for pedestrians' 3D bounding box prediction. This method follows an encoder-decoder architecture based on recurrent neural networks, and our experiments show its effectiveness in both the synthetic (JTA) and real-world (NuScenes) datasets. The learned representation has useful information to enhance the performance of other tasks, such as action anticipation. Our code is available online: https://github.com/vita-epfl/bounding-box-prediction
While a considerable amount of semantic parsing approaches have employed RNN architectures for code generation tasks, there have been only few attempts to investigate the applicability of Transformers for this task. Including hierarchical information of the underlying programming language syntax has proven to be effective for code generation. Since the positional encoding of the Transformer can only represent positions in a flat sequence, we have extended the encoding scheme to allow the attention mechanism to also attend over hierarchical positions in the input. Furthermore, we have realized a decoder based on a restrictive grammar graph model to improve the generation accuracy and ensure the well-formedness of the generated code. While we did not surpass the state of the art, our findings suggest that employing a tree-based positional encoding in combination with a shared natural-language subword vocabulary improves generation performance over sequential positional encodings.
Graph self-supervised learning (SSL) has been vastly employed to learn representations from unlabeled graphs. Existing methods can be roughly divided into predictive learning and contrastive learning, where the latter one attracts more research attention with better empirical performance. We argue that, however, predictive models weaponed with powerful decoder could achieve comparable or even better representation power than contrastive models. In this work, we propose a Wiener Graph Deconvolutional Network (WGDN), an augmentation-adaptive decoder empowered by graph wiener filter to perform information reconstruction. Theoretical analysis proves the superior reconstruction ability of graph wiener filter. Extensive experimental results on various datasets demonstrate the effectiveness of our approach.
Defocus blur is a physical consequence of the optical sensors used in most cameras. Although it can be used as a photographic style, it is commonly viewed as an image degradation modeled as the convolution of a sharp image with a spatially-varying blur kernel. Motivated by the advance of blur estimation methods in the past years, we propose a non-blind approach for image deblurring that can deal with spatially-varying kernels. We introduce two encoder-decoder sub-networks that are fed with the blurry image and the estimated blur map, respectively, and produce as output the deblurred (deconvolved) image. Each sub-network presents several skip connections that allow data propagation from layers spread apart, and also inter-subnetwork skip connections that ease the communication between the modules. The network is trained with synthetically blur kernels that are augmented to emulate blur maps produced by existing blur estimation methods, and our experimental results show that our method works well when combined with a variety of blur estimation methods.
This report presents the algorithm used in the submission of Generic Event Boundary Detection (GEBD) Challenge at CVPR 2022. In this work, we improve the existing Structured Context Transformer (SC-Transformer) method for GEBD. Specifically, a transformer decoder module is added after transformer encoders to extract high quality frame features. The final classification is performed jointly on the results of the original binary classifier and a newly introduced multi-class classifier branch. To enrich motion information, optical flow is introduced as a new modality. Finally, model ensemble is used to further boost performance. The proposed method achieves 86.49% F1 score on Kinetics-GEBD test set. which improves 2.86% F1 score compared to the previous SOTA method.
This competition focus on Urban-Sense Segmentation based on the vehicle camera view. Class highly unbalanced Urban-Sense images dataset challenge the existing solutions and further studies. Deep Conventional neural network-based semantic segmentation methods such as encoder-decoder architecture and multi-scale and pyramid-based approaches become flexible solutions applicable to real-world applications. In this competition, we mainly review the literature and conduct experiments on transformer-driven methods especially SegFormer, to achieve an optimal trade-off between performance and efficiency. For example, SegFormer-B0 achieved 74.6% mIoU with the smallest FLOPS, 15.6G, and the largest model, SegFormer- B5 archived 80.2% mIoU. According to multiple factors, including individual case failure analysis, individual class performance, training pressure and efficiency estimation, the final candidate model for the competition is SegFormer- B2 with 50.6 GFLOPS and 78.5% mIoU evaluated on the testing set. Checkout our code implementation at https://vmv.re/cv3315.
Recent works in autonomous driving have widely adopted the bird's-eye-view (BEV) semantic map as an intermediate representation of the world. Online prediction of these BEV maps involves non-trivial operations such as multi-camera data extraction as well as fusion and projection into a common topview grid. This is usually done with error-prone geometric operations (e.g., homography or back-projection from monocular depth estimation) or expensive direct dense mapping between image pixels and pixels in BEV (e.g., with MLP or attention). In this work, we present 'LaRa', an efficient encoder-decoder, transformer-based model for vehicle semantic segmentation from multiple cameras. Our approach uses a system of cross-attention to aggregate information over multiple sensors into a compact, yet rich, collection of latent representations. These latent representations, after being processed by a series of self-attention blocks, are then reprojected with a second cross-attention in the BEV space. We demonstrate that our model outperforms the best previous works using transformers on nuScenes. The code and trained models are available at https://github.com/valeoai/LaRa
Ophthalmic images may contain identical-looking pathologies that can cause failure in automated techniques to distinguish different retinal degenerative diseases. Additionally, reliance on large annotated datasets and lack of knowledge distillation can restrict ML-based clinical support systems' deployment in real-world environments. To improve the robustness and transferability of knowledge, an enhanced feature-learning module is required to extract meaningful spatial representations from the retinal subspace. Such a module, if used effectively, can detect unique disease traits and differentiate the severity of such retinal degenerative pathologies. In this work, we propose a robust disease detection architecture with three learning heads, i) A supervised encoder for retinal disease classification, ii) An unsupervised decoder for the reconstruction of disease-specific spatial information, and iii) A novel representation learning module for learning the similarity between encoder-decoder feature and enhancing the accuracy of the model. Our experimental results on two publicly available OCT datasets illustrate that the proposed model outperforms existing state-of-the-art models in terms of accuracy, interpretability, and robustness for out-of-distribution retinal disease detection.
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework of spatiotemporal predictive learning, in which the spatial encoder and decoder capture intra-frame features and the middle temporal module catches inter-frame correlations. While the mainstream methods employ recurrent units to capture long-term temporal dependencies, they suffer from low computational efficiency due to their unparallelizable architectures. To parallelize the temporal module, we propose the Temporal Attention Unit (TAU), which decomposes the temporal attention into intra-frame statical attention and inter-frame dynamical attention. Moreover, while the mean squared error loss focuses on intra-frame errors, we introduce a novel differential divergence regularization to take inter-frame variations into account. Extensive experiments demonstrate that the proposed method enables the derived model to achieve competitive performance on various spatiotemporal prediction benchmarks.
As information sources are usually imperfect, it is necessary to take into account their reliability in multi-source information fusion tasks. In this paper, we propose a new deep framework allowing us to merge multi-MR image segmentation results using the formalism of Dempster-Shafer theory while taking into account the reliability of different modalities relative to different classes. The framework is composed of an encoder-decoder feature extraction module, an evidential segmentation module that computes a belief function at each voxel for each modality, and a multi-modality evidence fusion module, which assigns a vector of discount rates to each modality evidence and combines the discounted evidence using Dempster's rule. The whole framework is trained by minimizing a new loss function based on a discounted Dice index to increase segmentation accuracy and reliability. The method was evaluated on the BraTs 2021 database of 1251 patients with brain tumors. Quantitative and qualitative results show that our method outperforms the state of the art, and implements an effective new idea for merging multi-information within deep neural networks.
Recent work has shown that generation from a prompted or fine-tuned language model can perform well at semantic parsing when the output is constrained to be a valid semantic representation. We introduce BenchCLAMP, a Benchmark to evaluate Constrained LAnguage Model Parsing, that includes context-free grammars for seven semantic parsing datasets and two syntactic parsing datasets with varied output representations, as well as a constrained decoding interface to generate only valid outputs covered by these grammars. We provide low, medium, and high resource splits for each dataset, allowing accurate comparison of various language models under different data regimes. Our benchmark supports evaluation of language models using prompt-based learning as well as fine-tuning. We benchmark eight language models, including two GPT-3 variants available only through an API. Our experiments show that encoder-decoder pretrained language models can achieve similar performance or surpass state-of-the-art methods for syntactic and semantic parsing when the model output is constrained to be valid.
Linking neural representations to linguistic factors is crucial in order to build and analyze NLP models interpretable by humans. Among these factors, syntactic roles (e.g. subjects, direct objects,$\dots$) and their realizations are essential markers since they can be understood as a decomposition of predicative structures and thus the meaning of sentences. Starting from a deep probabilistic generative model with attention, we measure the interaction between latent variables and realizations of syntactic roles and show that it is possible to obtain, without supervision, representations of sentences where different syntactic roles correspond to clearly identified different latent variables. The probabilistic model we propose is an Attention-Driven Variational Autoencoder (ADVAE). Drawing inspiration from Transformer-based machine translation models, ADVAEs enable the analysis of the interactions between latent variables and input tokens through attention. We also develop an evaluation protocol to measure disentanglement with regard to the realizations of syntactic roles. This protocol is based on attention maxima for the encoder and on latent variable perturbations for the decoder. Our experiments on raw English text from the SNLI dataset show that $\textit{i)}$ disentanglement of syntactic roles can be induced without supervision, $\textit{ii)}$ ADVAE separates syntactic roles better than classical sequence VAEs and Transformer VAEs, $\textit{iii)}$ realizations of syntactic roles can be separately modified in sentences by mere intervention on the associated latent variables. Our work constitutes a first step towards unsupervised controllable content generation. The code for our work is publicly available.
Recent studies in lossy compression show that distortion and perceptual quality are at odds with each other, which put forward the tradeoff between distortion and perception (D-P). Intuitively, to attain different perceptual quality, different decoders have to be trained. In this paper, we present a nontrivial finding that only two decoders are sufficient for optimally achieving arbitrary (an infinite number of different) D-P tradeoff. We prove that arbitrary points of the D-P tradeoff bound can be achieved by a simple linear interpolation between the outputs of a minimum MSE decoder and a specifically constructed perfect perceptual decoder. Meanwhile, the perceptual quality (in terms of the squared Wasserstein-2 distance metric) can be quantitatively controlled by the interpolation factor. Furthermore, to construct a perfect perceptual decoder, we propose two theoretically optimal training frameworks. The new frameworks are different from the distortion-plus-adversarial loss based heuristic framework widely used in existing methods, which are not only theoretically optimal but also can yield state-of-the-art performance in practical perceptual decoding. Finally, we validate our theoretical finding and demonstrate the superiority of our frameworks via experiments. Code is available at: https://github.com/ZeyuYan/Controllable-Perceptual-Compression
We describe an approach used in the Generic Boundary Event Captioning challenge at the Long-Form Video Understanding Workshop held at CVPR 2022. We designed a Rich Encoder-decoder framework for Video Event CAptioner (REVECA) that utilizes spatial and temporal information from the video to generate a caption for the corresponding the event boundary. REVECA uses frame position embedding to incorporate information before and after the event boundary. Furthermore, it employs features extracted using the temporal segment network and temporal-based pairwise difference method to learn temporal information. A semantic segmentation mask for the attentional pooling process is adopted to learn the subject of an event. Finally, LoRA is applied to fine-tune the image encoder to enhance the learning efficiency. REVECA yielded an average score of 50.97 on the Kinetics-GEBC test data, which is an improvement of 10.17 over the baseline method. Our code is available in https://github.com/TooTouch/REVECA.
Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference, non-autoregressive (NAR) methods, e.g. single-step NAR, were designed, to enable parallel generation. However, due to an independence assumption within the output tokens, performance of single-step NAR is inferior to that of AR models, especially with a large-scale corpus. There are two challenges to improving single-step NAR: Firstly to accurately predict the number of output tokens and extract hidden variables; secondly, to enhance modeling of interdependence between output tokens. To tackle both challenges, we propose a fast and accurate parallel transformer, termed Paraformer. This utilizes a continuous integrate-and-fire based predictor to predict the number of tokens and generate hidden variables. A glancing language model (GLM) sampler then generates semantic embeddings to enhance the NAR decoder's ability to model context interdependence. Finally, we design a strategy to generate negative samples for minimum word error rate training to further improve performance. Experiments using the public AISHELL-1, AISHELL-2 benchmark, and an industrial-level 20,000 hour task demonstrate that the proposed Paraformer can attain comparable performance to the state-of-the-art AR transformer, with more than 10x speedup.