What is new ? Not much, under the pressure of getting LLMs to be either faster or more specialized LoRAs are center stage with a multitudes of approaches.
Oh, and an agent helps in building the page.
Know of a decomposition or factorization technique or an implementation or a phase transition that's missing? Open an issue and mention the paper reference (arxiv, bioxiv, DOI, techrxiv, etc....) where you found it, a brief description of the factorization or decomposition (a new one or one that has already been identified in the page), and ideally a link to code/repo. If you have identified a phase transition, please mention the article and the figure in which it is viewable (as a bound or as a graph).
A curated list of resources on implicit neural representations, inspired by awesome-computer-vision. Work-in-progress.
This list does not aim to be exhaustive, as implicit neural representations are a rapidly evolving & growing research field with hundreds of papers to date.
Instead, this list aims to list papers introducing key concepts & foundations of implicit neural representations across applications. It's a great reading list if you want to get started in this area!
For most papers, there is a short summary of the most important contributions.
Disclosure: I am an author on the following papers:
Implicit Neural Representations (sometimes also referred to coordinate-based representations) are a novel way to parameterize signals of all kinds. Conventional signal representations are usually discrete - for instance, images are discrete grids of pixels, audio signals are discrete samples of amplitudes, and 3D shapes are usually parameterized as grids of voxels, point clouds, or meshes. In contrast, Implicit Neural Representations parameterize a signal as a continuous function that maps the domain of the signal (i.e., a coordinate, such as a pixel coordinate for an image) to whatever is at that coordinate (for an image, an R,G,B color). Of course, these functions are usually not analytically tractable - it is impossible to "write down" the function that parameterizes a natural image as a mathematical formula. Implicit Neural Representations thus approximate that function via a neural network.
Why are they interesting?
Implicit Neural Representations have several benefits: First, they are not coupled to spatial resolution anymore, the way, for instance, an image is coupled to the number of pixels. This is because they are continuous functions! Thus, the memory required to parameterize the signal is independent of spatial resolution, and only scales with the complexity of the underyling signal. Another corollary of this is that implicit representations have "infinite resolution" - they can be sampled at arbitrary spatial resolutions.
This is immediately useful for a number of applications, such as super-resolution, or in parameterizing signals in 3D and higher dimensions, where memory requirements grow intractably fast with spatial resolution.
However, in the future, the key promise of implicit neural representations lie in algorithms that directly operate in the space of these representations. In other words: What's the "convolutional neural network" equivalent of a neural network operating on images represented by implicit representations? Questions like these offer a path towards a class of algorithms that are independent of spatial resolution!..........
I just want to share a Github repo that I am maintaining for Deep Learning based compressive sensing and our recent paper toward multi-scale deep compressive sensing.
Abstract: With joint learning of the sampling and recovery, the deep learning-based compressive sensing (DCS) has shown significant improvement in performance and running time reduction. Its reconstructed image, however, losses high-frequency content especially at low subrates. It is understood due to relatively much low-frequency information captured into the sampling matrix. This behavior happens similarly in the multi-scale sampling scheme which also samples more low-frequency components. This paper proposes a multi-scale DCS (MS-DCSNet) based on convolutional neural network. Firstly, we convert image signal using multiple scale-based wavelet transform. Then, the signal is captured through the convolution block by block across scales. The initial reconstructed image is directly recovered from multi-scale measurements. Multi-scale wavelet convolution is utilized to enhance the final reconstruction quality. The network learns to perform both multi-scale in sampling and reconstruction thus results in better reconstruction quality.
Deep learning-based compressive sensing (DCS) has improved the compressive sensing (CS) with fast and high reconstruction quality. Researchers have further extended it to multi-scale DCS which improves reconstruction quality based on Wavelet decomposition. In this work, we mimic the Difference of Gaussian via convolution and propose a scheme named as Difference of convolution-based multi-scale DCS (DoC-DCS). Unlike the multi-scale DCS based on a well-designed filter in the wavelet domain, the proposed DoC-DCS learns decomposition, thereby, outperforms other state-of-the-art compressive sensing methods.
i hope all goes well. FYI, the Rice CS Archive is back online after being down for more than a year thanks to some Russian hackers who thought we had something to do with the 2018 election. it’s available here:
So last night I was talking to Thomas at the STMicroelectronics Techno day at Opera de Paris. He was featuring a recent architecture they are designing and presented at the last ISSC conference.
Every week, new papers on Generative Adversarial Networks (GAN) are coming out and it’s hard to keep track of them all, not to mention the incredibly creative ways in which researchers are naming these GANs! You can read more about GANs in this Generative Models post by OpenAI or this overview tutorial in KDNuggets.
Avinash also mentions that the list can be expanded:
You can visit the Github repository to add more links via pull requests or create an issue to lemme know something I missed or to start a discussion.
The subject is so hot that there is an earlier and somewhat more complete page on the subject
