We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adaptor networks that map the input to be compatible with a network trained on large-scale color image datasets such as ImageNet. Adaptors enable learning on small hyperspectral datasets where training a network from scratch may not be effective. We investigate architectures and strategies for training adaptors and evaluate them on a benchmark consisting of multiple hyperspectral datasets. We find that simple schemes such as linear projection or subset selection are often the most effective, but can lead to a loss in performance in some cases. We also propose a novel multi-view adaptor where of the inputs are combined in an intermediate layer of the network in an order invariant manner that provides further improvements. We present extensive experiments by varying the number of training examples in the benchmark to characterize the accuracy and computational trade-offs offered by these adaptors.
We present cross-view transformers, an efficient attention-based model for map-view semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping from individual camera views into a canonical map-view representation using a camera-aware cross-view attention mechanism. Each camera uses positional embeddings that depend on its intrinsic and extrinsic calibration. These embeddings allow a transformer to learn the mapping across different views without ever explicitly modeling it geometrically. The architecture consists of a convolutional image encoder for each view and cross-view transformer layers to infer a map-view semantic segmentation. Our model is simple, easily parallelizable, and runs in real-time. The presented architecture performs at state-of-the-art on the nuScenes dataset, with 4x faster inference speeds. Code is available at https://github.com/bradyz/cross_view_transformers.
We consider the problem of Multi-view 3D Face Reconstruction (MVR) with weakly supervised learning that leverages a limited number of 2D face images (e.g. 3) to generate a high-quality 3D face model with very light annotation. Despite their encouraging performance, present MVR methods simply concatenate multi-view image features and pay less attention to critical areas (e.g. eye, brow, nose and mouth). To this end, we propose a novel model called Deep Fusion MVR (DF-MVR) and design a multi-view encoding to a single decoding framework with skip connections, able to extract, integrate, and compensate deep features with attention from multi-view images. In addition, we develop a multi-view face parse network to learn, identify, and emphasize the critical common face area. Finally, though our model is trained with a few 2D images, it can reconstruct an accurate 3D model even if one single 2D image is input. We conduct extensive experiments to evaluate various multi-view 3D face reconstruction methods. Our proposed model attains superior performance, leading to 11.4% RMSE improvement over the existing best weakly supervised MVRs. Source codes are available in the supplementary materials.
Optics and photonics has recently captured interest as a platform to accelerate linear matrix processing, that has been deemed as a bottleneck in traditional digital electronic architectures. In this paper, we propose an all-photonic artificial neural network processor wherein information is encoded in the amplitudes of frequency modes that act as neurons. The weights among connected layers are encoded in the amplitude of controlled frequency modes that act as pumps. Interaction among these modes for information processing is enabled by non-linear optical processes. Both the matrix multiplication and element-wise activation functions are performed through coherent processes, enabling the direct representation of negative and complex numbers without the use of detectors or digital electronics. Via numerical simulations, we show that our design achieves a performance commensurate with present-day state-of-the-art computational networks on image-classification benchmarks. Our architecture is unique in providing a completely unitary, reversible mode of computation. Additionally, the computational speed increases with the power of the pumps to arbitrarily high rates, as long as the circuitry can sustain the higher optical power.
With the ubiquity of rolling shutter (RS) cameras, it is becoming increasingly attractive to recover the latent global shutter (GS) video from two consecutive RS frames, which also places a higher demand on realism. Existing solutions, using deep neural networks or optimization, achieve promising performance. However, these methods generate intermediate GS frames through image warping based on the RS model, which inevitably result in black holes and noticeable motion artifacts. In this paper, we alleviate these issues by proposing a context-aware GS video reconstruction architecture. It facilitates the advantages such as occlusion reasoning, motion compensation, and temporal abstraction. Specifically, we first estimate the bilateral motion field so that the pixels of the two RS frames are warped to a common GS frame accordingly. Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times. Furthermore, we derive an approximated bilateral motion field model, which can serve as an alternative to provide a simple but effective GS frame initialization for related tasks. Experiments on synthetic and real data show that our approach achieves superior performance over state-of-the-art methods in terms of objective metrics and subjective visual quality. Code is available at \url{https://github.com/GitCVfb/CVR}.
The U-Net architecture, built upon the fully convolutional network, has proven to be effective in biomedical image segmentation. However, U-Net applies skip connections to merge semantically different low- and high-level convolutional features, resulting in not only blurred feature maps, but also over- and under-segmented target regions. To address these limitations, we propose a simple, yet effective end-to-end depthwise encoder-decoder fully convolutional network architecture, called Sharp U-Net, for binary and multi-class biomedical image segmentation. The key rationale of Sharp U-Net is that instead of applying a plain skip connection, a depthwise convolution of the encoder feature map with a sharpening kernel filter is employed prior to merging the encoder and decoder features, thereby producing a sharpened intermediate feature map of the same size as the encoder map. Using this sharpening filter layer, we are able to not only fuse semantically less dissimilar features, but also to smooth out artifacts throughout the network layers during the early stages of training. Our extensive experiments on six datasets show that the proposed Sharp U-Net model consistently outperforms or matches the recent state-of-the-art baselines in both binary and multi-class segmentation tasks, while adding no extra learnable parameters. Furthermore, Sharp U-Net outperforms baselines that have more than three times the number of learnable parameters.
In this paper, we present a novel framework that can achieve multimodal image-to-image translation by simply encouraging the statistical dependence between the latent code and the output image in conditional generative adversarial networks. In addition, by incorporating a U-net generator into our framework, our method only needs to learn a one-sided translation model from the source image domain to the target image domain for both supervised and unsupervised multimodal image-to-image translation. Furthermore, our method also achieves disentanglement between the source domain content and the target domain style for free. We conduct experiments under supervised and unsupervised settings on various benchmark image-to-image translation datasets compared with the state-of-the-art methods, showing the effectiveness and simplicity of our method to achieve multimodal and high-quality results.
We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure attributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending to produce a plausible swapping result. We further extend our method to video face swapping by enforcing two spatio-temporal constraints on the latent space and the image space. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art image/video face swapping methods in terms of hallucination quality and consistency. Code can be found at: https://github.com/cnnlstm/FSLSD_HiRes.
Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments, the contrastive learning has emerged as an effective technique to substantially enhance the deep clustering performance. However, the existing contrastive learning based deep clustering algorithms mostly focus on some carefully-designed augmentations (often with limited transformations to preserve the structure), referred to as weak augmentations, but cannot go beyond the weak augmentations to explore the more opportunities in stronger augmentations (with more aggressive transformations or even severe distortions). In this paper, we present an end-to-end deep clustering approach termed strongly augmented contrastive clustering (SACC), which extends the conventional two-augmentation-view paradigm to multiple views and jointly leverages strong and weak augmentations for strengthened deep clustering. Particularly, we utilize a backbone network with triply-shared weights, where a strongly augmented view and two weakly augmented views are incorporated. Based on the representations produced by the backbone, the weak-weak view pair and the strong-weak view pairs are simultaneously exploited for the instance-level contrastive learning (via an instance projector) and the cluster-level contrastive learning (via a cluster projector), which, together with the backbone, can be jointly optimized in a purely unsupervised manner. Experimental results on five challenging image datasets have shown the superior performance of the proposed SACC approach over the state-of-the-art.
Designing implants for large and complex cranial defects is a challenging task, even for professional designers. Current efforts on automating the design process focused mainly on convolutional neural networks (CNN), which have produced state-of-the-art results on reconstructing synthetic defects. However, existing CNN-based methods have been difficult to translate to clinical practice in cranioplasty, as their performance on complex and irregular cranial defects remains unsatisfactory. In this paper, a statistical shape model (SSM) built directly on the segmentation masks of the skulls is presented. We evaluate the SSM on several cranial implant design tasks, and the results show that, while the SSM performs suboptimally on synthetic defects compared to CNN-based approaches, it is capable of reconstructing large and complex defects with only minor manual corrections. The quality of the resulting implants is examined and assured by experienced neurosurgeons. In contrast, CNN-based approaches, even with massive data augmentation, fail or produce less-than-satisfactory implants for these cases. Codes are publicly available at https://github.com/Jianningli/ssm